{"total":25,"rows":[{"id":"2405.09831","title":"Nearly Minimax Optimal Regret for Multinomial Logistic Bandit","created":"2024-05-16","cited_by_count":20,"area":null},{"id":"2312.08057","title":"Combinatorial Stochastic-Greedy Bandit","created":"2023-12-13","cited_by_count":18,"area":null},{"id":"2101.01301","title":"Adversarial Combinatorial Bandits with General Non-linear Reward Functions","created":"2021-01-05","cited_by_count":14,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2102.07800","title":"Top-$k$ eXtreme Contextual Bandits with Arm Hierarchy","created":"2021-02-15","cited_by_count":8,"area":null},{"id":"2408.11202","title":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2102.12722","title":"Combinatorial Bandits under Strategic Manipulations","created":"2021-02-25","cited_by_count":6,"area":null},{"id":"2103.01453","title":"Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure","created":"2021-03-02","cited_by_count":5,"area":null},{"id":"2108.00230","title":"Pure Exploration and Regret Minimization in Matching Bandits","created":"2021-07-31","cited_by_count":4,"area":null},{"id":"2112.13029","title":"Gaussian Process Bandits with Aggregated Feedback","created":"2021-12-24","cited_by_count":3,"area":null},{"id":"2305.16074","title":"Combinatorial Bandits for Maximum Value Reward Function under Max Value-Index Feedback","created":"2023-05-25","cited_by_count":3,"area":null},{"id":"2501.00924","title":"On the Low-Complexity of Fair Learning for Combinatorial Multi-Armed Bandit","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2303.13604","title":"Stochastic Submodular Bandits with Delayed Composite Anonymous Bandit Feedback","created":"2023-03-23","cited_by_count":2,"area":null},{"id":"2407.00567","title":"A Contextual Combinatorial Bandit Approach to Negotiation","created":"2024-06-30","cited_by_count":2,"area":null},{"id":"2601.05597","title":"Good Allocations from Bad Estimates","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2405.12439","title":"No-Regret M${}^{\\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and Hardness of Adversarial Full-Information Setting","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2408.03405","title":"Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous Agents","created":"2024-08-06","cited_by_count":1,"area":null},{"id":"2502.18709","title":"Bandit and Delayed Feedback in Online Structured Prediction","created":"2025-02-26","cited_by_count":1,"area":null},{"id":"2107.02738","title":"Dueling Bandits with Team Comparisons","created":"2021-07-06","cited_by_count":0,"area":null},{"id":"2212.05190","title":"Neural Bandits for Data Mining: Searching for Dangerous Polypharmacy","created":"2022-12-10","cited_by_count":0,"area":null},{"id":"2308.12680","title":"Master-slave Deep Architecture for Top-K Multi-armed Bandits with Non-linear Bandit Feedback and Diversity Constraints","created":"2023-08-24","cited_by_count":0,"area":null},{"id":"2512.24708","title":"BandiK: Efficient Multi-Task Decomposition Using a Multi-Bandit Framework","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2512.24959","title":"Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learning","created":"2025-12-31","cited_by_count":0,"area":null},{"id":"2605.00762","title":"Meritocratic Fairness via $K$-Shapley Values in Budgeted Combinatorial Bandits with Full-Bandit Feedback","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2608.22120","title":"The Price of Decentralization in Top-$K$ Arm Identification","created":"2026-08-22","cited_by_count":0,"area":null}],"next_cursor":null}